Comments (2)
I noticed the same thing, using the file-based SimpleVectorDb
.
The documents used as "ground facts" are the ones being "closest" to your query, where "closest" is defined using cosine similarity. I found that this kind of similarity often retrieves documents that have nothing to do with the subject at hand.
For example, queries like "How do I do X?" will retrieve documents where X (or something related to X) doesn't even occur.
I am investigating why this is. But this of course never happens with keyword search. Documents containing X would be retrieved by definition.
This is all very strange. The investigation continues.
You can find out which facts are being selected by placing a breakpoint at the call of SearchClient.GenerateAnswerAsyncin SearchClient
.
from kernel-memory.
Actually in my case facts are correct but OpenAI ignores them completely.
from kernel-memory.
Related Issues (20)
- [Question] MemoryFilter mixing conditions HOT 3
- [Bug] "contentType" is not populated by WriteFileAsync in MongoDbAtlasStorage HOT 1
- [Bug] Content Storage File handles not properly disposed HOT 2
- [Question] Is there any way to get the list of documents? HOT 2
- [Feature Request] Support batching upsert in SQL Server Memory DB HOT 1
- IndexNotFound should be renamed to IndexNotFoundException
- [Question] does content.url in filename for websites make sense? (I want attribution per paragraph via separate prompt) HOT 4
- [Question] Regarding Hard-coded Elastic index vector dimension size HOT 1
- [Question] Running Kernel Memory as a service in Asp.Net HOT 1
- [Bug] Can't publish HOT 2
- Kernel Memory on kubernetes HOT 6
- [Question] public to internal HOT 4
- [Bug] MemoryWebClient - Rewind stream before posting to server HOT 1
- [Question] How to optimize the cost of each Ask?
- This model's maximum context length is 8192 tokens - question HOT 2
- [Question] Reading document status HOT 2
- [Question] Export imported Documents HOT 3
- [Bug] SQL failing to save when too many tags with the same key are present (list/content too big for the key) HOT 2
- GraphRAG Support HOT 1
- Support Managed Identity Authentication for AI Search HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kernel-memory.